learning-dynamics

Tag

Cards List
#learning-dynamics

Empirical Characterization of Learning Geometry in Hybrid Quantum Forecasting Models

arXiv cs.LG · yesterday Cached

The paper empirically characterizes the learning geometry of hybrid quantum forecasting models, comparing them to classical baselines using Neural Tangent Kernel dynamics and other metrics, showing that similar generalization can emerge from different optimization trajectories.

0 favorites 0 likes
#learning-dynamics

Pseudospectral Bounds for Transient Amplification in Coupled Gradient Descent

arXiv cs.LG · 2026-06-04 Cached

This paper develops a sharp pseudospectral theory for block-triangular Jacobians in coupled gradient descent, proving Kreiss-constant bounds and establishing iteration complexity results. The work exposes non-asymptotic, instance-dependent transient amplification phenomena relevant to bilevel optimization, two-time-scale stochastic approximation, and GAN training.

0 favorites 0 likes
#learning-dynamics

Support Before Frequency in Discrete Diffusion

arXiv cs.LG · 2026-05-15 Cached

This paper proposes the 'support-before-frequency' hypothesis for discrete diffusion models, suggesting that models first learn the support (admissible sequences) before refining frequencies within the support. Theoretical analysis of small-noise reverse kernels and experiments on masked language diffusion models support this claim.

0 favorites 0 likes
#learning-dynamics

State-Space NTK Collapse Near Bifurcations

arXiv cs.LG · 2026-05-14 Cached

This paper develops a local theory of gradient descent near bifurcations in dynamical models, showing that the state-space neural tangent kernel collapses to a rank-one operator that dominates learning dynamics, making optimization effectively low-dimensional and predictable from normal forms.

0 favorites 0 likes
← Back to home

Submit Feedback